ai-safety-foundation / sparse_autoencoderLinks
Sparse Autoencoder for Mechanistic Interpretability
☆248Updated 10 months ago
Alternatives and similar repositories for sparse_autoencoder
Users that are interested in sparse_autoencoder are comparing it to the libraries listed below
Sorting:
- Using sparse coding to find distributed representations used by neural networks.☆247Updated last year
- ☆302Updated 2 weeks ago
- ☆223Updated 8 months ago
- Sparsify transformers with SAEs and transcoders☆553Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- Mechanistic Interpretability Visualizations using React☆253Updated 5 months ago
- ☆97Updated last month
- ☆124Updated 6 months ago
- ☆121Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆181Updated this week
- Training Sparse Autoencoders on Language Models☆802Updated last week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆579Updated this week
- ☆171Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆155Updated last year
- ☆43Updated 6 months ago
- ☆480Updated 10 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆103Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆116Updated this week
- ☆117Updated 10 months ago
- This repository collects all relevant resources about interpretability in LLMs☆353Updated 7 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆93Updated last year
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆44Updated last year
- Sparse probing paper full code.☆56Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆223Updated 8 months ago
- ☆93Updated 3 months ago
- ☆209Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- ☆83Updated 9 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month